© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 129734
    Prev
    Next
    INDEX
    Explanations

    foreign words and examples

    np_acts-logits-general · gemini-2.5-flash-lite

    default assumptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    spiration
    0.60
    LED
    0.49
     at
    0.48
     quarter
    0.47
    ква
    0.47
    те
    0.47
    ковых
    0.46
    ık
    0.46
    H
    0.45
    Ы
    0.45
    POSITIVE LOGITS
     exemples
    0.52
     deportiva
    0.52
     فوتب
    0.49
     書い
    0.49
     gacche
    0.48
     pavatt
    0.47
     ब्रेन
    0.47
     そんな
    0.46
     เห็น
    0.46
     مثال
    0.46
    Activations Density 0.000%

    No Known Activations